Computer Sciences Commons^™

Visual And Lingual Emotion Recognition Using Deep Learning Techniques, Akshay Kajale

Master's Projects

Emotion recognition has been an integral part of many applications like video games, cognitive computing, and human computer interaction. Emotion can be recognized by many sources including speech, facial expressions, hand gestures and textual attributes. We have developed a prototype emotion recognition system using computer vision and natural language processing techniques. Our goal hybrid system uses mobile camera frames and features abstracted from speech named Mel Frequency Cepstral Coefficient (MFCC) to recognize the emotion of a person. To acknowledge the emotions based on facial expressions, we have developed a Convolutional Neural Network (CNN) model, which has an accuracy of 68%. …

Has Excessive Violence In Video Games Gone Too Far?, Kyra Sycip

ART 108: Introduction to Games Studies

Numerous case studies and published research have led many gamers and non-gamers to wonder whether the excessive loads of violence found in video games is truly necessary for “fun” gameplay and entertainment. Controversies have been arising within famous video games such as the Grand Theft Auto series, Call Of Duty: Modern Warfare 2, and Six Days in Fallujah. These three games have been the subject of numerous present day debates and have sparked many arguments within the gaming community. As well as the debate of whether these games are indeed harmful to the player’s psychology and nature has yet to …

Enhancing Usability Of Malware Analysis Pipelines With Reverse Engineering, Jeffrey Ching

Theses - ALL

Lots of work has been done on analyzing software distributed in binary form. This is a challenging problem because of the relatively unstructured nature of binaries. To recover high-level structure, various attempts have included static and dynamic analysis. However, human inspection is often required, as high-level structure is compiled away. Recent success in this area includes work on variable-name recovery, vulnerability discovery, class recovery for object-oriented languages. We are interested in building a pipeline for user to analyze malware. In this thesis we tackle two problems central to malware analysis pipelines. The first is D3RE, an interactive querying tool that …

Internet Of Medical Things (Iomt): Overview, Emerging Technologies, And Case Studies, Sahshanu Razdan, Sachin Sharma

Articles

No abstract provided.

Sentiment Classification Bias In User Generated Content, Alpana Deshpande

Theses - ALL

Interactive websites generate terabytes of data on a daily basis. This data canbe used in multiple analytical applications to teach computers more about human behavior. Text classification is such an application. Multiple freely available user-generated text data can be used to teach computers to identify the sentiments behind a user's on-screen interactions without the need of any human intervention. Sentiment analysis is an interesting problem, solving which would theoretically get a computer closer to passing the Turing test. Through this thesis, we test the ability of a classifier to accurately identify user sentiments. However, we do not focus on standard …

Inferring Degree Of Localization Of Twitter Persons And Topics Through Time, Language, And Location Features, Aleksey Valeriy Panasyuk

Dissertations - ALL

Identifying authoritative influencers related to a geographic area (geo-influencers) can aid content recommendation systems and local expert finding. This thesis addresses this important problem using Twitter data.

A geo-influencer is identified via the locations of its followers. On Twitter, due to privacy reasons, the location reported by followers is limited to profile via a textual string or messages with coordinates. However, this textual string is often not possible to geocode and less than 1\% of message traffic provides coordinates. First, the error rates associated with Google's geocoder are studied and a classifier is built that gives a warning for self-reported …

Experience-Driven Control For Networking And Computing, Zhiyuan Xu

Dissertations - ALL

Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …

Year-Independent Prediction Of Food Insecurity Using Classical & Neural Network Machine Learning Methods, Caleb Christiansen, Torrey J. Wagner, Brent Langhals

Faculty Publications

Current food crisis predictions are developed by the Famine Early Warning System Network, but they fail to classify the majority of food crisis outbreaks with model metrics of recall (0.23), precision (0.42), and f1 (0.30). In this work, using a World Bank dataset, classical and neural network (NN) machine learning algorithms were developed to predict food crises in 21 countries. The best classical logistic regression algorithm achieved a high level of significance (p < 0.001) and precision (0.75) but was deficient in recall (0.20) and f1 (0.32). Of particular interest, the classical algorithm indicated that the vegetation index and the food price index were both positively correlated with food crises. A novel method for performing an iterative multidimensional hyperparameter search is presented, which resulted in significantly improved performance when applied to this dataset. Four iterations were conducted, which resulted in excellent 0.96 for metrics of precision, recall, and f1. Due to this strong performance, the food crisis year was removed from the dataset to prevent immediate extrapolation when used on future data, and the modeling process was repeated. The best “no year” model metrics remained strong, achieving ≥0.92 for recall, precision, and f1 while meeting a 10% f1 overfitting threshold on the test (0.84) and holdout (0.83) datasets. The year-agnostic neural network model represents a novel approach to classify food crises and outperforms current food crisis prediction efforts.

Sentiment Classification Bias In User Generated Content, Alpana Deshpande

Theses - ALL

Interactive websites generate terabytes of data on a daily basis. This data canbe used in multiple analytical applications to teach computers more about human behavior. Text classification is such an application. Multiple freely available user-generated text data can be used to teach computers to identify the sentiments behind a user’s on-screen interactions without the need of any human intervention. Sentiment analysis is an interesting problem, solving which would theoretically get a computer closer to passing the Turing test. Through this thesis, we test the ability of a classifier to accurately identify user sentiments. However, we do not focus on standard …

Using An Integrative Machine Learning Approach To Study Microrna Regulation Networks In Pancreatic Cancer Progression, Roland Madadjim

School of Computing: Dissertations, Theses, and Student Research

With advances in genomic discovery tools, recent biomedical research has produced a massive amount of genomic data on post-transcriptional regulations related to various transcript factors, microRNAs, lncRNAs, epigenetic modifications, and genetic variations. In this direction, the field of gene regulation network inference is created and aims to understand the interactome regulations between these molecules (e.g., gene-gene, miRNA-gene) that take place to build models able to capture behavioral changes in biological systems. A question of interest arises in integrating such molecules to build a network while treating each specie in its uniqueness. Given the dynamic changes of interactome in chaotic systems …

Enhancing Usability Of Malware Analysis Pipelines With Reverse Engineering, Jeffrey Ching

Theses - ALL

Lots of work has been done on analyzing software distributed in binary form. This is a challenging problem because of the relatively unstructured nature of binaries. To recover high-level structure, various attempts have included static and dynamic analysis. However, human inspection is often required, as high-level structure is compiled away. Recent success in this area includes work on variable-name recovery, vulnerability discovery, class recovery for object-oriented languages. We are interested in building a pipeline for user to analyze malware. In this thesis we tackle two problems central to malware analysis pipelines. The first is D3RE, an interactive querying tool that …

Inferring Degree Of Localization Of Twitter Persons And Topics Through Time, Language, And Location Features, Aleksey Valeriy Panasyuk

Dissertations - ALL

Identifying authoritative influencers related to a geographic area (geo-influencers) can aid content recommendation systems and local expert finding. This thesis addresses this important problem using Twitter data.

A geo-influencer is identified via the locations of its followers. On Twitter, due to privacy reasons, the location reported by followers is limited to profile via a textual string or messages with coordinates. However, this textual string is often not possible to geocode and less than 1\% of message traffic provides coordinates. First, the error rates associated with Google's geocoder are studied and a classifier is built that gives a warning for self-reported …

Experience-Driven Control For Networking And Computing, Zhiyuan Xu

Dissertations - ALL

Modern networking and computing systems have become very complicated and highly dynamic, which makes them hard to model, predict and control. In this thesis, we aim to study system control problems from a whole new perspective by leveraging emerging Deep Reinforcement Learning (DRL), to develop experience-driven model-free approaches, which enable a network or a device to learn the best way to control itself from its own experience (e.g., runtime statistics data) rather than from accurate mathematical models, just as a human learns a new skill (e.g., driving, swimming, etc). To demonstrate the feasibility and superiority of this experience-driven control design …

Knowing What We Know: Leveraging Community Knowledge Through Automated Text-Mining, Justin Gardner, Jonathan Tory Toole, Hemant Kalia, Garry Spink Jr., Gordon Broderick

Advances in Clinical Medical Research and Healthcare Delivery

No abstract provided.

How This War Of Mine Creates Empathy For Virtual Characters, Cole Pergerson

ART 108: Introduction to Games Studies

Is it possible to empathize with virtual characters? Are game characters just a means for game and story progress or can we develop a strong emotional connection with them? In this research essay, I analysis This War of Mine, a game about surviving a worn torn city where food is limited, and the player must make difficult moral decisions survive. The player controls a small group of characters who all need to be feed, get enough sleep, may need medical care, and other human needs. To look how This War of Mine creates empathy for the virtual characters, I will …

Accelerating Multigrid-Based Hierarchical Scientific Data Refactoring On Gpus, Jieyang Chen, Lipeng Wan, Xin Liang, Ben Whitney, For Full List Of Authors, See Publisher's Website.

Computer Science Faculty Research & Creative Works

Rapid growth in scientific data and a widening gap between computational speed and I/O bandwidth make it increasingly infeasible to store and share all data produced by scientific simulations. Instead, we need methods for reducing data volumes: ideally, methods that can scale data volumes adaptively so as to enable negotiation of performance and fidelity tradeoffs in different situations. Multigrid-based hierarchical data representations hold promise as a solution to this problem, allowing for flexible conversion between different fidelities so that, for example, data can be created at high fidelity and then transferred or stored at lower fidelity via logically simple and …

Revisiting Huffman Coding: Toward Extreme Performance On Modern Gpu Architectures, Jiannan Tian, Cody Rivera, Sheng Di, Jieyang Chen, Xin Liang, Dingwen Tao, Franck Cappello

Computer Science Faculty Research & Creative Works

Today’s high-performance computing (HPC) applications are producing vast volumes of data, which are challenging to store and transfer efficiently during the execution, such that data compression is becoming a critical technique to mitigate the storage burden and data movement cost. Huffman coding is arguably the most efficient Entropy coding algorithm in information theory, such that it could be found as a fundamental step in many modern compression algorithms such as DEFLATE. On the other hand, today’s HPC applications are more and more relying on the accelerators such as GPU on supercomputers, while Huffman encoding suffers from low throughput on GPUs, …

Human/Artificial Intelligence Coordination In Video Games, Michael Rodriguez

ART 108: Introduction to Games Studies

The emergence of video games has led to widespread inventions to enhance the reality of the experience. As a result, Artificial Intelligence (A.I.) was developed to create virtual experiences and attract a variety of players of video games. This paper will discuss video games in the context of Human-A.I. interaction and the importance of human coordination in video games. Unprecedented errors have been a common challenge in this relationship. An excellent example of these algorithms include population-based training and self-play, which have gained a lot of interest in video games. A.I. technology has surpassed human ability because they are simply …

Federated Learning In Gaze Recognition (Fligr), Arun Gopal Govindaswamy

College of Computing and Digital Media Dissertations

The efficiency and generalizability of a deep learning model is based on the amount and diversity of training data. Although huge amounts of data are being collected, these data are not stored in centralized servers for further data processing. It is often infeasible to collect and share data in centralized servers due to various medical data regulations. This need for diversely distributed data and infeasible storage solutions calls for Federated Learning (FL). FL is a clever way of utilizing privately stored data in model building without the need for data sharing. The idea is to train several different models locally …

Deep Learning Predicts Chromosomal Instability From Histopathology Images, Zhuoran Xu, Akanksha Verma, Uska Naveed, Samuel F. Bakhoum, Pegah Khosravi, Olivier Elemento

Publications and Research

Chromosomal instability (CIN) is a hallmark of human cancer yet not readily testable for patients with cancer in routine clinical setting. In this study, we sought to explore whether CIN status can be predicted using ubiquitously available hematoxylin and eosin histology through a deep learning-based model. When applied to a cohort of 1,010 patients with breast cancer (Training set: n = 858, Test set: n = 152) from The Cancer Genome Atlas where 485 patients have high CIN status, our model accurately classified CIN status, achieving an area under the curve of 0.822 with 81.2% sensitivity and 68.7% specificity in …

Improving Additional Adversarial Robustness For Classification, Michael Guo

McKelvey School of Engineering Graduate Student Theses & Dissertations

Although neural networks have achieved remarkable success on classification, adversarial robustness is still a significant concern. There are now a series of approaches for designing adversarial examples and methods to defending against them. This paper consists of two projects. In our first work, we propose an approach by leveraging cognitive salience to enhance additional robustness on top of these methods. Specifically, for image classification, we split an image into the foreground (salient region) and background (the rest) and allow significantly larger adversarial perturbations in the background to produce stronger attacks. Furthermore, we show that adversarial training with dual-perturbation attacks yield …

Real-Time Monitoring Of Fdm 3d Printer For Fault Detection Using Machine Learning: A Bibliometric Study, Vaibhav Kisan Kadam, Satish Kumar, Arunkumar Bongale

Library Philosophy and Practice (e-journal)

Additive Manufacturing has wide application range including healthcare, Fashion, Manufacturing, Prototypes, Tooling etc. AM techniques are subjected to various defects that may be printing defects or anomalies in machine. There is gap between current AM techniques and smart manufacturing since current AM lacks in build sensors necessary for process monitoring and fault detection. Both of these issues can be solved by incorporating real-time monitoring into AM. So the study is carried out to identify recent work done in AM to improve current system. For this bibliometric study Scopus database is used, study is kept limited to year 2010-2021 and English …

Proceedings Of The First And Second Seminar On Responsible Computing, Alicia M. Grubb, Sarah Abowitz, Maha Awaisi, Hannah Clemens, Jenna Croteau, Barb Garrison, You Jeen Ha, Winnie Mbugua, Mayeline Peña, Sarah Swihart, Ratidzo Vushe, Suzie Xi

Other Student Projects

No abstract provided.

Optimizing Blockchain Based Smart Grid Auctions: A Green Revolution, Muneeb Ul Hassan, Mubashir Husain Rehmani, Jinjun Chen

Preprints

Integrating blockchain with energy trading is a new paradigm for researchers working in the field of smart grid. In energy trading, auction theory plays an important role to ensure truthfulness, rationality, and to balance utility of participants. However, traditional energy auctions cannot directly be integrated in blockchain based auctions due to the decentralized nature. Therefore, researches are being carried out to propose more efficient decentralized auctions for energy trading. Despite of all these advances, a greater standpoint that is not well-highlighted or discussed in majority of proposed mechanisms is the integration of green aspect in these auctions. Since, blockchain is …

Pitcher Effectiveness: A Step Forward For In Game Analytics And Pitcher Evaluation, Christopher Watkins, Vincent Berardi, Cyril Rakovski

Mathematics, Physics, and Computer Science Faculty Articles and Research

With the introduction of Statcast in 2015, baseball analytics have become more precise. Statcast allows every play to be accurately tracked and the data it generates is easily accessible through Baseball Savant, which opens the opportunity for improved performance statistics to be developed. In this paper we propose a new tool, Pitcher Effectiveness, that uses Statcast data to evaluate starting pitchers dynamically, based on the results of in-game outcomes after each pitch. Pitcher Effectiveness successfully predicts instances where starting pitchers give up several runs, which we believe make it a new and important tool for the in-game and post-game evaluation …

If You Only Knew The Power Of The Dark Web! Finding Intellectual Freedom, Privacy, And Anonymity Online, Daniel W. Jolley

Dover Library Faculty Professional Development Activities

While the dark web attracts largely negative and sensationalistic headlines as a haven for criminality, it (and the tools used to access it) also offers knowledgeable users the ability to surf the web free of government surveillance and social media/marketing tracking and to exercise free speech in an environment of virtual anonymity. As such, the dark web supports librarians’ values regarding privacy and intellectual freedom. This presentation will give librarians a realistic look at both the positive and negative aspects of the dark web, provide them with examples of the types of users who may want to explore or make …

A Highly-Parameterized Ensemble To Play Gin Rummy, Masayuki Nagai '22, Kavya Shrivastava '23, Kien Ta '22, Steven Bogaerts, Chad Byers

Computer Science Faculty publications

This paper describes the design and training of a computer Gin Rummy player. The system includes three main components to make decisions about drawing cards, discarding, and ending the game, with numerous parameters controlling behavior. In particular, an ensemble approach is explored in the discard decision. Finally, three sets of parameter tuning and performance experiments are analyzed.

Self-Supervised Learning For Fine-Grained Visual Categorization, Muhammad Maaz, Hanoona Abdul Rasheed, Dhanalaxmi Gaddam

Student Publications

Recent research in self-supervised learning (SSL) has shown its capability in learning useful semantic representations from images for classification tasks. Through our work, we study the usefulness of SSL for Fine-Grained Visual Categorization (FGVC). FGVC aims to distinguish objects of visually similar subcategories within a general category. The small inter-class, but large intra-class variations within the dataset makes it a challenging task. The limited availability of annotated labels for such fine-grained data encourages the need for SSL, where additional supervision can boost learning without the cost of extra annotations. Our baseline achieves 86.36% top-1 classification accuracy on CUB-200-2011 dataset by …

Asynchronous Validations Using Programming Contracts In Java, Rahul Shukla

Master's Projects

Design by Contract is a software development methodology based on the idea of having contracts between two software components. Programming contracts are invariants specified as pre-conditions and post-conditions. The client component must ensure that all the pre-conditions are satisfied before calling the server component. The server component must guarantee the post-conditions are met before the call returns to the client component. Current work in Design by Contract in Java focuses on writing shorthand contracts using annotations that are processed serially.

Modern software systems require a lot of business rules validations on complicated domain objects. Often, such validations are in the …

Moonshine: An Online Randomness Distiller For Zero-Involvement Authentication, Jack West, Kyuin Lee, Suman Banerjee, Younghyun Kim, George K. Thiruvathukal, Neil Klingensmith

Computer Science: Faculty Publications and Other Works

Context-based authentication is a method for transparently validating another device's legitimacy to join a network based on location. Devices can pair with one another by continuously harvesting environmental noise to generate a random key with no user involvement. However, there are gaps in our understanding of the theoretical limitations of environmental noise harvesting, making it difficult for researchers to build efficient algorithms for sampling environmental noise and distilling keys from that noise. This work explores the information-theoretic capacity of context-based authentication mechanisms to generate random bit strings from environmental noise sources with known properties. Using only mild assumptions about the …